Keep Calm and Switch On! Preserving Sentiment and Fluency in Semantic Text Exchange
By Steven Y. Feng, Aaron W. Li, Jesse Hoey. 2019
31 citations recorded by the source corpus.
In this paper, we present a novel method for measurably adjusting the semantics of text while preserving its sentiment and fluency, a task we call semantic text exchange. This is useful for text data augmentation and the semantic correction of text generated by chatbots and virtual assistants. We introduce a pipeline called SMERTI that combines entity replacement, similarity masking, and text infilling. We measure our pipeline’s success by its Semantic Text Exchange Score (STES): the ability to preserve the original text’s sentiment and fluency while adjusting semantic content. We propose to use masking (replacement) rate threshold as an adjustable parameter to control the amount of semantic change in the text. Our experiments demonstrate that SMERTI can outperform baseline models on Yelp reviews, Amazon reviews, and news headlines.
Subfields: Artificial Intelligence, Information Systems, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Varun Prashant Gangal
- Eduard H. Hovy
- Teruko Mitamura
- Soroush Vosoughi
- Steven Y. Feng
- Jason Wei
- Sarath Chandar
- Dongyeop Kang
In Information Systems
- Varun Prashant Gangal
- Eduard H. Hovy
- Teruko Mitamura
- Jason Wei
- Sarath Chandar
- Steven Y. Feng
- Mirella Lapata
- Chin-Yew Lin
In Natural Language Processing
- Varun Prashant Gangal
- Eduard H. Hovy
- Teruko Mitamura
- Soroush Vosoughi
- Jason Wei
- Steven Y. Feng
- Sarath Chandar
- Dongyeop Kang
Citations in the corpus
- A Survey of Data Augmentation Approaches for NLP (2021, background): “There are many works which have investigated DA for NMT.”
- GenAug: Data Augmentation for Finetuning Text Generators (2020, methodology): “We explore various augmentation methods such as semantic text exchange (STE) (Feng et al., 2019) and replacing keywords within examples from a small subset of the Yelp Reviews dataset (Yelp).”
- NAREOR: The Narrative Reordering Problem (2021, methodology): “Future directions include exploring training ideas better emulating human rewriting, such as methods like Semantic Text Exchange (Feng et al., 2019) to adjust output text.”